-;;; thai-util.el --- utilities for Thai
+;;; thai-util.el --- utilities for Thai -*- coding: iso-2022-7bit; -*-
;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
;; Boston, MA 02111-1307, USA.
-;;; Code:
+;;; Commentary:
-;;;###autoload
-(defun setup-thai-environment ()
- "Setup multilingual environment (MULE) for Thai."
- (interactive)
- (set-language-environment "Thai"))
+;;; Code:
;; Setting information of Thai characters.
-(defvar thai-category-table (copy-category-table))
-(or (category-docstring ?+ thai-category-table)
- (define-category ?+ "Thai consonant" thai-category-table))
-(or (category-docstring ?- thai-category-table)
- (define-category ?- "Thai diacritical mark" thai-category-table))
+(defconst thai-category-table (make-category-table))
+(define-category ?c "Thai consonant" thai-category-table)
+(define-category ?v "Thai upper/lower vowel" thai-category-table)
+(define-category ?t "Thai tone" thai-category-table)
+
+;; The general composing rules are as follows:
+;;
+;; T
+;; V T V T
+;; CV -> C, CT -> C, CVT -> C, Cv -> C, CvT -> C
+;; v v
+;;
+;; where C: consonant, V: vowel upper, v: vowel lower, T: tone mark.
+
+(defvar thai-composition-pattern "\\cc\\(\\ct\\|\\cv\\ct?\\)"
+ "Regular expression matching a Thai composite sequence.")
(let ((l '((?\e,T!\e(B consonant "LETTER KO KAI") ; 0xA1
(?\e,T"\e(B consonant "LETTER KHO KHAI") ; 0xA2
(?\e,T|\e(B invalid nil) ; 0xFC
(?\e,T}\e(B invalid nil) ; 0xFD
(?\e,T~\e(B invalid nil) ; 0xFE
+
+ ;; Unicode equivalents
+ (?\e$,1Ba\e(B consonant "LETTER KO KAI")
+ (?\e$,1Bb\e(B consonant "LETTER KHO KHAI")
+ (?\e$,1Bc\e(B consonant "LETTER KHO KHUAT")
+ (?\e$,1Bd\e(B consonant "LETTER KHO KHWAI")
+ (?\e$,1Be\e(B consonant "LETTER KHO KHON")
+ (?\e$,1Bf\e(B consonant "LETTER KHO RAKHANG")
+ (?\e$,1Bg\e(B consonant "LETTER NGO NGU")
+ (?\e$,1Bh\e(B consonant "LETTER CHO CHAN")
+ (?\e$,1Bi\e(B consonant "LETTER CHO CHING")
+ (?\e$,1Bj\e(B consonant "LETTER CHO CHANG")
+ (?\e$,1Bk\e(B consonant "LETTER SO SO")
+ (?\e$,1Bl\e(B consonant "LETTER CHO CHOE")
+ (?\e$,1Bm\e(B consonant "LETTER YO YING")
+ (?\e$,1Bn\e(B consonant "LETTER DO CHADA")
+ (?\e$,1Bo\e(B consonant "LETTER TO PATAK")
+ (?\e$,1Bp\e(B consonant "LETTER THO THAN")
+ (?\e$,1Bq\e(B consonant "LETTER THO NANGMONTHO")
+ (?\e$,1Br\e(B consonant "LETTER THO PHUTHAO")
+ (?\e$,1Bs\e(B consonant "LETTER NO NEN")
+ (?\e$,1Bt\e(B consonant "LETTER DO DEK")
+ (?\e$,1Bu\e(B consonant "LETTER TO TAO")
+ (?\e$,1Bv\e(B consonant "LETTER THO THUNG")
+ (?\e$,1Bw\e(B consonant "LETTER THO THAHAN")
+ (?\e$,1Bx\e(B consonant "LETTER THO THONG")
+ (?\e$,1By\e(B consonant "LETTER NO NU")
+ (?\e$,1Bz\e(B consonant "LETTER BO BAIMAI")
+ (?\e$,1B{\e(B consonant "LETTER PO PLA")
+ (?\e$,1B|\e(B consonant "LETTER PHO PHUNG")
+ (?\e$,1B}\e(B consonant "LETTER FO FA")
+ (?\e$,1B~\e(B consonant "LETTER PHO PHAN")
+ (?\e$,1B\7f\e(B consonant "LETTER FO FAN")
+ (?\e$,1C \e(B consonant "LETTER PHO SAMPHAO")
+ (?\e$,1C!\e(B consonant "LETTER MO MA")
+ (?\e$,1C"\e(B consonant "LETTER YO YAK")
+ (?\e$,1C#\e(B consonant "LETTER RO RUA")
+ (?\e$,1C$\e(B vowel-base "LETTER RU (Pali vowel letter)")
+ (?\e$,1C%\e(B consonant "LETTER LO LING")
+ (?\e$,1C&\e(B vowel-base "LETTER LU (Pali vowel letter)")
+ (?\e$,1C'\e(B consonant "LETTER WO WAEN")
+ (?\e$,1C(\e(B consonant "LETTER SO SALA")
+ (?\e$,1C)\e(B consonant "LETTER SO RUSI")
+ (?\e$,1C*\e(B consonant "LETTER SO SUA")
+ (?\e$,1C+\e(B consonant "LETTER HO HIP")
+ (?\e$,1C,\e(B consonant "LETTER LO CHULA")
+ (?\e$,1C-\e(B consonant "LETTER O ANG")
+ (?\e$,1C.\e(B consonant "LETTER HO NOK HUK")
+ (?\e$,1C/\e(B special "PAI YAN NOI (abbreviation)")
+ (?\e$,1C0\e(B vowel-base "VOWEL SIGN SARA A")
+ (?\e$,1C1\e(B vowel-upper "VOWEL SIGN MAI HAN-AKAT N/S-T")
+ (?\e$,1C2\e(B vowel-base "VOWEL SIGN SARA AA")
+ (?\e$,1C3\e(B vowel-base "VOWEL SIGN SARA AM")
+ (?\e$,1C4\e(B vowel-upper "VOWEL SIGN SARA I N/S-T")
+ (?\e$,1C5\e(B vowel-upper "VOWEL SIGN SARA II N/S-T")
+ (?\e$,1C6\e(B vowel-upper "VOWEL SIGN SARA UE N/S-T")
+ (?\e$,1C7\e(B vowel-upper "VOWEL SIGN SARA UEE N/S-T")
+ (?\e$,1C8\e(B vowel-lower "VOWEL SIGN SARA U N/S-B")
+ (?\e$,1C9\e(B vowel-lower "VOWEL SIGN SARA UU N/S-B")
+ (?\e$,1C:\e(B vowel-lower "VOWEL SIGN PHINTHU N/S-B (Pali virama)")
+ (?\e$,1C?\e(B special "BAHT SIGN (currency symbol)")
+ (?\e$,1C@\e(B vowel-base "VOWEL SIGN SARA E")
+ (?\e$,1CA\e(B vowel-base "VOWEL SIGN SARA AE")
+ (?\e$,1CB\e(B vowel-base "VOWEL SIGN SARA O")
+ (?\e$,1CC\e(B vowel-base "VOWEL SIGN SARA MAI MUAN")
+ (?\e$,1CD\e(B vowel-base "VOWEL SIGN SARA MAI MALAI")
+ (?\e$,1CE\e(B vowel-base "LAK KHANG YAO")
+ (?\e$,1CF\e(B special "MAI YAMOK (repetion)")
+ (?\e$,1CG\e(B vowel-upper "VOWEL SIGN MAI TAI KHU N/S-T")
+ (?\e$,1CH\e(B tone "TONE MAI EK N/S-T")
+ (?\e$,1CI\e(B tone "TONE MAI THO N/S-T")
+ (?\e$,1CJ\e(B tone "TONE MAI TRI N/S-T")
+ (?\e$,1CK\e(B tone "TONE MAI CHATTAWA N/S-T")
+ (?\e$,1CL\e(B tone "THANTHAKHAT N/S-T (cancellation mark)")
+ (?\e$,1CM\e(B tone "NIKKHAHIT N/S-T (final nasal)")
+ (?\e$,1CN\e(B vowel-upper "YAMAKKAN N/S-T")
+ (?\e$,1CO\e(B special "FONRMAN")
+ (?\e$,1CP\e(B special "DIGIT ZERO")
+ (?\e$,1CQ\e(B special "DIGIT ONE")
+ (?\e$,1CR\e(B special "DIGIT TWO")
+ (?\e$,1CS\e(B special "DIGIT THREE")
+ (?\e$,1CT\e(B special "DIGIT FOUR")
+ (?\e$,1CU\e(B special "DIGIT FIVE")
+ (?\e$,1CV\e(B special "DIGIT SIX")
+ (?\e$,1CW\e(B special "DIGIT SEVEN")
+ (?\e$,1CX\e(B special "DIGIT EIGHT")
+ (?\e$,1CY\e(B special "DIGIT NINE")
+ (?\e$,1CZ\e(B special "ANGKHANKHU (ellipsis)")
+ (?\e$,1C[\e(B special "KHOMUT (beginning of religious texts)")
))
elm)
(while l
- (setq elm (car l))
- (let ((ptype (nth 1 elm)))
- (put-char-code-property (car elm) 'phonetic-type ptype)
- (if (eq ptype 'consonant)
- (modify-category-entry (car elm) ?+ thai-category-table)
- (if (memq ptype '(vowel-upper vowel-lower tone))
- (modify-category-entry (car elm) ?- thai-category-table))))
- (put-char-code-property (car elm) 'name (nth 2 elm))
- (setq l (cdr l))))
-
+ (setq elm (car l) l (cdr l))
+ (let ((char (car elm))
+ (ptype (nth 1 elm)))
+ (put-char-code-property char 'phonetic-type ptype)
+ (cond ((eq ptype 'consonant)
+ (modify-category-entry char ?c thai-category-table))
+ ((memq ptype '(vowel-upper vowel-lower))
+ (modify-category-entry char ?v thai-category-table))
+ ((eq ptype 'tone)
+ (modify-category-entry char ?t thai-category-table)))
+ (put-char-code-property char 'name (nth 2 elm)))))
;;;###autoload
(defun thai-compose-region (beg end)
(interactive "r")
(save-restriction
(narrow-to-region beg end)
- (decompose-region (point-min) (point-max))
(goto-char (point-min))
- (let ((current-ctbl (category-table)))
- (set-category-table thai-category-table)
- (unwind-protect
- (while (re-search-forward "\\c+\\c-+" nil t)
- (compose-region (match-beginning 0) (match-end 0)))
- (set-category-table current-ctbl)))))
+ (with-category-table thai-category-table
+ (while (re-search-forward thai-composition-pattern nil t)
+ (compose-region (match-beginning 0) (match-end 0))))))
+;;;###autoload
+(defun thai-compose-string (string)
+ "Compose Thai characters in STRING and return the resulting string."
+ (with-category-table thai-category-table
+ (let ((idx 0))
+ (while (setq idx (string-match thai-composition-pattern string idx))
+ (compose-string string idx (match-end 0))
+ (setq idx (match-end 0)))))
+ string)
+
;;;###autoload
(defun thai-compose-buffer ()
"Compose Thai characters in the current buffer."
;;;###autoload
(defun thai-post-read-conversion (len)
- (save-excursion
- (save-restriction
- (let ((buffer-modified-p (buffer-modified-p)))
- (narrow-to-region (point) (+ (point) len))
- (thai-compose-region (point-min) (point-max))
- (set-buffer-modified-p buffer-modified-p)
- (- (point-max) (point-min))))))
+ (thai-compose-region (point) (+ (point) len))
+ len)
;;;###autoload
-(defun thai-pre-write-conversion (from to)
- (let ((old-buf (current-buffer)))
- (set-buffer (generate-new-buffer " *temp*"))
- (if (stringp from)
- (insert from)
- (insert-buffer-substring old-buf from to))
- (decompose-region (point-min) (point-max))
- ;; Should return nil as annotations.
- nil))
+(defun thai-composition-function (from to pattern &optional string)
+ "Compose Thai text in the region FROM and TO.
+The text matches the regular expression PATTERN.
+Optional 4th argument STRING, if non-nil, is a string containing text
+to compose.
+
+The return value is number of composed characters."
+ (if (< (1+ from) to)
+ (progn
+ (if string
+ (compose-string string from to)
+ (compose-region from to))
+ (- to from))))
;;
(provide 'thai-util)